Improved Minimax Bounds on the Test and Training Distortion of Empirically Designed Vector Quantizers

DOI10.1109/TIT.2005.856980zbMath1284.94038MaRDI QIDQ3546515

András Antos

Publication date: 21 December 2008

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Mathematics Subject Classification ID

Source coding (94A29)

Related Items (9)

Convergence of the $k$-Means Minimization Problem using $\Gamma$-Convergence ⋮ Fast rates for empirical vector quantization ⋮ Statistical learning guarantees for compressive clustering and compressive mixture modeling ⋮ Empirical risk minimization for heavy-tailed losses ⋮ On Hölder fields clustering ⋮ A notion of stability for \(k\)-means clustering ⋮ Dimensionality-Dependent Generalization Bounds for k-Dimensional Coding Schemes ⋮ Robust \(k\)-means clustering for distributions with two moments ⋮ Nonasymptotic bounds for vector quantization in Hilbert spaces

This page was built for publication: Improved Minimax Bounds on the Test and Training Distortion of Empirically Designed Vector Quantizers